<chadmed>
Dcow[m]1: surprise i did the descriptions today
<rqou_>
decided to start taking a peek at the prores encoder, and does anybody know what changed in a dart,t8110? or why the M1 Max would have that in the ADT?
<rqou_>
isn't that supposed to be the A15?
<chadmed>
i made a PR against asahi-installer upstream if you want to grab them to use while youre testing stuff
<chadmed>
they probably just dropped the prores block in with no changes so that they didnt need to change kexts etc
<tpw_rules>
chadmed: might be nice to note on the uefi description that your distro also has to have a compatible kernel
<rqou_>
the prores, scaler, and usb4(?) all use the dart,t8110
<tpw_rules>
also does anyone call it a "systemready/EBBR image"
<chadmed>
ive seen quite a few distros advertise being able to boot uefi on arm as having support for SR/EBBR so its worth mentioning
<tpw_rules>
ah ok. i hadn't
<chadmed>
RHEL and Fedora are the main ones
<chadmed>
also are T600x DTs due to be merged into 5.18?
<nicolas17>
rqou_: that is indeed A15... "backported" dart block?
<rqou_>
i haven't looked at the behavior / register interface to see if it's any different yet
<rqou_>
i would first want to figure out how to even drive the prores block from macos userspace
<rqou_>
i've never really worked with macos at all
<rqou_>
oh yeah, AVD on the M1 Max also seems to use dart,t8110 (but not AVE?)
doggkruse has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
<alyssa>
rqou_: fwiw, usb4 ~= thunderbolt
doggkruse has joined #asahi-dev
<tpw_rules>
is that "approximately equal"
<alyssa>
yea
<alyssa>
I mean. I think. I just do graphics.
<tpw_rules>
ok. in some bad programming languages it's "not equal"
<chadmed>
whoever decided that should be NEQ needs to be shot out of a cannon into the sun
<kevans91>
hey now, lua isn't that bad
<chadmed>
along with whoever decided null > 0 should be truthful in javascript
<tpw_rules>
i more meant MATLAB®
<kevans91>
to be fair, it does seem a pretty natural expression when ~ is viewed as 'bitwise NOT'
<chadmed>
its particularly egregious in a language called MATLAB, when in MAThematics ~ is and basically always has been "approximately"
* kevans91
nods
<tpw_rules>
it's actually MATrix thank you very much
<Jamie[m]1>
the AVD has a lot of messy stuff going on with DMA I don’t understand so I didn’t want to RE both unknowns at the same time, I wonder if it’d be easiest to figure it out with Scaler since I assume from the name that’s probably pretty simple?
<rqou_>
it Should(TM) be possible to figure out the DART just by guessing?
<rqou_>
i wouldn't want to be the one who had to verify whether or not i guessed right though
<Jamie[m]1>
probably for someone who knows more about this than me :P
<Jamie[m]1>
there were so many acronyms i didn’t recognise that my eyes glazed over
<rqou_>
yeah, i'm definitely not super familiar with acronym soup
<rqou_>
IOMMUs shouldn't be that complicated though
<rqou_>
according to the m1n1 experiment the only difference between the t8020 and t6000 DART is the PTEs though, so the register dump might not be enough
<Jamie[m]1>
yeah, this one definitely rearranges register blocks
<Jamie[m]1>
and iirc also introduces a new register
<Jamie[m]1>
*block
<Jamie[m]1>
or at least there's a one newly named in the driver that was never given a name in the old driver
<nicolas17>
"didn't want to RE both unknowns at the same time"
doggkruse has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
<nicolas17>
Jamie[m]1: would it be easier to RE AVD on the M1 with the older DART then?
<Jamie[m]1>
i suppose so, if i had one :)
<nicolas17>
well sure, just checking if I understood the situation :)
doggkruse has joined #asahi-dev
<rqou_>
doing DART+scaler might also make sense
<rqou_>
it's interesting how apple keeps upgrading these "legacy" hardware blocks
<Jamie[m]1>
the first DART upgrade was to allow for more physical addressable memory right?
<rqou_>
yeah
<rqou_>
suddenly reminded of an unrelated question: alyssa do you have any idea what a kCVPixelFormatType_AGX_420YpCbCr8BiPlanarFullRange might be? it's a "compressed" image format that the JPEG encoder for some reason has special support for, but i don't know much about what it actually is
kov has quit [Quit: Coyote finally caught me]
kov has joined #asahi-dev
user982492 has joined #asahi-dev
doggkruse has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
<Jamie[m]1>
sidetracked while investigating that: why does corevideo have Direct3D/DXGI pixel formats lmao
<chadmed>
it's just one of the pixel formats AGX has support for. 8-bit YCbCr 4:2:0 subsampling
<Jamie[m]1>
I'm not sure if that makes sense
<nicolas17>
chadmed was probably answering your *previous* question :P
<nicolas17>
the D3D thing is probably for nvidia cards?
<Jamie[m]1>
rqou's question, you mean?
<chadmed>
yeah i was answering rqou's question heh, should have tagged them sorry
<nicolas17>
oh looks like I'm even more confused
<rqou_>
it's definitely not just 8-bit ycbcr since it has its own entire separate codepath in the jpeg driver
<chadmed>
seems ridiculous that AGX would support PAL pixel formats in anno domini 2022 but... well there you go
<rqou_>
"PAL" in the webkit context probably just means platform abstraction layer
<nicolas17>
^
<chadmed>
or yeah i could just be stupid, that definitely makes more sense :P
<rqou_>
in any case, the jpeg driver has special handling for the '&8f0' fourcc (and several others) that causes something completely different to happen
<rqou_>
the only reference i can find to that is an offhand mention in webkit
<chadmed>
the pixel format is defined in the corevideo public api, the only difference being the AGX specifier
<chadmed>
could just be that AGX has or once had a special codepath for accelerating this pixel format, and they use this internally to tell the jpeg block to offload it or something
<rqou_>
it even gets its own entire separate block of registers
<rqou_>
i.e. not the registers that are used to encode normal 4:2:0 ycbcr (kCVPixelFormatType_420YpCbCr8BiPlanarFullRange)
<chadmed>
ok buried in the PAL changelog
<chadmed>
there was a patch in 2020 to treat the _AGX_ variants the same as the ones without _AGX_ in the name and just use WebGL to handle them
<chadmed>
theyre specifically called "internal compressed formats"
<rqou_>
yeah, that's the only public reference i found
<rqou_>
what is the internal format though? how is it compressed? why does it get its own special handling? not being a GPU/graphics/video person, i have no idea
<chadmed>
i think they just mean "internal" as in "not in the public api"
<Jamie[m]1>
chadmed: in any case, it's different to the non-agx one, because the non-agx one is not compressed
kettenis has quit [Server closed connection]
kettenis has joined #asahi-dev
<chadmed>
long shot then, could it have been something they used for Apple Intermediate Codec back when that was a thing?
<chadmed>
that was compressed YUV 4:2:0, but has been dropped in favour of ProRes 422
<rqou_>
i would guess something more s3tc-like
<rqou_>
but i have no idea, and the codepath for it uses a pile of extra registers, and i was hoping that somebody who knew graphics better could take a poke at it at some point
<chadmed>
either way given the total lack of information on it and the only reference to it being someone at apple making webkit not use it anymore, unless you catch macos doing something with it explicitly i would probably not even bother
<chadmed>
the jpeg block is super old and theres probably a bunch of stuff in the hardware that does not get used anymore
<rqou_>
eh, it's not strictly needed, but i try to document how the hardware actually behaves rather than just looking at what macos can do via its drivers
<rqou_>
also the jpeg block isn't "super" old even if it's old
<rqou_>
there's at least 3 major generations of the jpeg block
<chadmed>
oh yeah for sure and if we figure it out thatd be grand, all i mean is dont give yourself a headache over it or anything :)
vafanlignarde has quit [Server closed connection]
vafanlignarde has joined #asahi-dev
<chadmed>
oh could it be for offloading ASTC?
<chadmed>
that makes more sense than S3TC, since that only supports RGB 5:6:5
<chadmed>
and AGX has supported ASTC for ages
grange_c has quit [Server closed connection]
grange_c has joined #asahi-dev
<nicolas17>
oddly "ASTC support" is one of the things used to separate iOS ipsws
<nicolas17>
iPad_64bit_TouchID_13.7_17H35_Restore.ipsw vs iPad_64bit_TouchID_ASTC_13.7_17H35_Restore.ipsw
<chadmed>
are they both for the same ipad?
<nicolas17>
no, they are each for different sets of ipads
<nicolas17>
it seemed weird that ASTC support was a dimension to split devices by for this purpose
<chadmed>
AGX only got support for "full" ASTC with the A13 so that could be it
<chadmed>
yeah ok that makes sense
<chadmed>
before the A13, it only had support for low dynamic range ASTC
<chadmed>
hence the VideoRange and FullRange pixel formats
<chadmed>
so im guessting the IPSWs tagged with ASTC were built with some sort of flag to tell it the target device has full ASTC or something
<chadmed>
or it could just be apple reusing the acronym for something else
<chadmed>
just like how internally they never used to call Apple Intermediate Codec AIC, for obvious reasons
<nicolas17>
eg. separating ipsws based on iPhone screen size makes sense, that way they don't bloat 4.7" iPhones with images (like wallpapers which are *large*) that are only used on 5.5" iPhones
firefox317 has quit [Server closed connection]
<nicolas17>
but if the 4.7" iPhone ipsw has 3 different kernels for different devices, it's no big deal, so they do that instead of 3 different ipsws
firefox317 has joined #asahi-dev
<chadmed>
well it seems that it actually is for ASTC, because they only started tagging them with ASTC for devices after the A13
<nicolas17>
maybe 'having ASTC' is a stand in for other features that do justify different files but are more awkward to fit into a filename :)
<chadmed>
that actually is an odd way to tag them though, hmm
commandoline has quit [Server closed connection]
commandoline has joined #asahi-dev
manawyrm has quit [Server closed connection]
manawyrm has joined #asahi-dev
pg12 has quit [Server closed connection]
pg12 has joined #asahi-dev
tired has quit [Server closed connection]
tired has joined #asahi-dev
arekm has quit [Remote host closed the connection]
eloy_ has quit [Server closed connection]
eloy_ has joined #asahi-dev
lonjil has quit [Server closed connection]
lonjil has joined #asahi-dev
zorun has quit [Server closed connection]
zorun has joined #asahi-dev
hizonx has joined #asahi-dev
Foxboron has quit [Server closed connection]
Foxboron has joined #asahi-dev
Fanfwe has quit [Server closed connection]
Fanfwe has joined #asahi-dev
<Dcow[m]1>
chadmed: thank you very much!
flying_sausages_ has quit [Server closed connection]
flying_sausages has joined #asahi-dev
rikkaa has joined #asahi-dev
Chinese_soup has quit [Server closed connection]
Chinese_soup has joined #asahi-dev
jeffmiw has quit [Quit: Konversation terminated!]
jannau has quit [Server closed connection]
jannau has joined #asahi-dev
wCPO6 has quit [Server closed connection]
wCPO6 has joined #asahi-dev
milek7 has quit [Server closed connection]
milek7 has joined #asahi-dev
nicolas17 has quit [Quit: Konversation terminated!]
<Jamie[m]1>
I wiped my old manual m1n1 install when the installer came out – what's the process for getting set back up for running macOS under HV? The installer won't install a whole other macos, right?
<Jamie[m]1>
And the Developer Quickstart article is gone… is there a new recommended method?
user982492 has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
PthariensFlame[m] has quit [Server closed connection]
PthariensFlame[m] has joined #asahi-dev
<jannau>
supporting larger framebuffers in m1n1 is a little annoying as iboot only preallocates 2 l2 page tables. not sure if I'm motivated to handle that
<jannau>
I guess a maximal resolution of 5120x2252 is fine for HDMI as first step
<Dcow[m]1>
AFAIK there are no monitors with resolution more than 4k and HDMI
<Dcow[m]1>
most of hi-res monitors are DP(DP over thunderbolt)
bittin^ has quit []
<jannau>
5120x2160 display's with hdmi exists, beyond that probably just 8k TVs
bisko has joined #asahi-dev
<Dcow[m]1>
yeah, but it's either 30Hz or hdmi 2.1 and that is no such thing for mini or 2021 MBPs
<jannau>
this affects only devices with dp to hdmi as primary display interface, so only mini and studio which have both only hdmi 2.0
<jannau>
we can't prevent 30Hz though
<mps>
I have one old philips hdmi monitor with 4096x$huh, forgot exact number
<mps>
don't use it for about 2-3 years
<jannau>
would be fine up to a height of 2816 but I guess the height is 2160
phire has quit [Remote host closed the connection]
rikkaa has quit [Quit: Connection closed for inactivity]
Guest550 has joined #asahi-dev
amarioguy has quit [Ping timeout: 480 seconds]
amarioguy has joined #asahi-dev
psykose has quit [Remote host closed the connection]
Guest550 has quit []
<amarioguy>
apple's security documentation mentions some keys are disabled when something like Asahi Linux is booted, will this affect any future plans to use SEP? do we know what specific keys are disabled?
<jannau>
marcan: is there a reason why we keep x2r10g10b10? we can now switch properly to x8r8g8b8 and avoid the drm colorspace conversion code
hizonx has quit [Ping timeout: 480 seconds]
hizonx has joined #asahi-dev
bisko has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
<jannau>
not really worth rewriting m1n1 fb code for though
<alyssa>
rqou_: I haven't seen kCVPixelFormatType_AGX_420YpCbCr8BiPlanarFullRange, but if I had to guess --
<alyssa>
That's a regular 420YpCbCr8BiPlanarFullRange format (leaving that as an exercise), compressed with what Apple calls "AGX compression"
<alyssa>
i.e. the compression native to the GPU, which the GPU can both compress and decompress efficiently (while rendering and sampling respectively)
kameks has quit [Ping timeout: 480 seconds]
<maz>
jannau: IIRC, there was a bunch of u-boot changes to support that. I wonder if we could get rid of that by letting m1n1 switch to x8r8g8b8.
<alyssa>
The display controller also supports "AGX compression", so WindowServer can composite on the GPU and send the composited frame to the display without ever decompressing (which saves considerable memory b/w with hidpi)
<alyssa>
For the JPEG *encoder*, presumably that supports passing a compressed YUV frame from the GPU directly to the JPEG encoder
<alyssa>
At a guess, to support screenshots efficiently on some iPhone?
<alyssa>
AGX compression is a framebuffer compression scheme, meaning it optimizes for memory bandwidth as opposed to total memory usage
<alyssa>
(In fact total memory usage goes up.>)
<alyssa>
And prioritises efficeint encode in hardware over absolute best compression
<alyssa>
(Differs from ASTC which realistically cannot be encoded in real time)
<alyssa>
Framebuffer compression schemes are usually multiplanar, with a compressed data plane and a separate control plane
<alyssa>
...meaning they may need extra registers to point to the aux plane, and/or to configure the compressio
<jannau>
maz: the code is already in u-boot master, probably not worth the effort to yank it now. I'm more concerned concerned about running linux desktop on top of drm's unoptimized x8r8g8b8 to x2r10g10b10 conversion code
<alyssa>
I wouldn't worry about any of this for now, though
<alyssa>
(Or at all, for JPEG...)
<sven>
amarioguy: iirc it disables mostly drm keys and Apple Pay support and stuff like that
<maz>
jannau: ah, I hadn't realised it was merged already. no need to touch that then.
<jannau>
I would guess that jpeg decode -> dcp plane was the use case for framebuffer compression in the jpeg hw
<alyssa>
jannau: That too, rqou_ mentioned encoding though
<jannau>
ah, I missed that
the_lanetly_052 has joined #asahi-dev
amarioguy has quit [Ping timeout: 480 seconds]
bisko has joined #asahi-dev
yuyichao has joined #asahi-dev
amarioguy has joined #asahi-dev
bisko has quit [Read error: Connection reset by peer]
bisko has joined #asahi-dev
emsi has joined #asahi-dev
meowmomo1[m] has joined #asahi-dev
<kettenis>
cool, two critical fixes made it into u-boot 2022.04
Thib[m] has quit [Server closed connection]
Thib[m] has joined #asahi-dev
amarioguy has quit [Remote host closed the connection]
amarioguy has joined #asahi-dev
<jannau>
kettenis: \o/!
<jannau>
kettenis: any preference how to handle the memmap for the m1 ultra? it's literally the m1 max one with I/O duplicated at a fixed offset. I wrote it out for now but it is a little meh
* bluetail[m]
> <@_oftc_kettenis:matrix.org> cool, two critical fixes made it into u-boot 2022.04
* bluetail[m]
been told you cant give yourselfs shoulder pats, but you can haha
* bluetail[m]
gives virtual shoulder pat
* bluetail[m]
> <@_oftc_kettenis:matrix.org> cool, two critical fixes made it into u-boot 2022.04
* bluetail[m]
* gives virtual shoulder pat
<jannau>
on the other hand I'm not sure if I want to copy it m1 max one twice
MajorBiscuit has quit [Ping timeout: 480 seconds]
msmith12[m] has quit [Server closed connection]
msmith12[m] has joined #asahi-dev
nicolas17 has joined #asahi-dev
<kettenis>
jannau: I think my preference is to simply copy the m1 max map and add additional regions to it
<kettenis>
but maybe simply extending the m1 max map to be the m1 ultra map would work as well
<kettenis>
having additional I/O ranges for devices that aren't present shouldn't hurt
amarioguy has quit [Ping timeout: 480 seconds]
doggkruse has joined #asahi-dev
<jannau>
ok, I guess I'll just keep the duplicated table. We don't have to care about a couple of bytes extra binary size
bisko has quit [Read error: Connection reset by peer]
KrushnaDeore[m] has quit [Server closed connection]
KrushnaDeore[m] has joined #asahi-dev
amarioguy has joined #asahi-dev
minecrell has quit [Quit: Ping timeout (120 seconds)]
minecrell has joined #asahi-dev
* jannau
is still amazed that crashing dcp can break usb/nvme
<alyssa>
jannau: lol
<sven>
…how??
<sven>
i could see it breaking atcphy because it pokes some DP-phy registers
<sven>
but nvme? lol
<alyssa>
DCP: it just keeps growing
<nicolas17>
I'm reading chat logs and lol the DCP can alpha-composite?
<jannau>
I have no idea, cuurrent problem is that clobber the the pre-allocated syslog DVA with the framebuffer
<marcan>
nicolas17: that's normal for any modern display controller
<marcan>
Android has a whole thing for offloading part of the screen compositing to hardware
<marcan>
wayland compositors can do the same thing
<nicolas17>
I know a big part of early iOS performance was offloading as much compositing/animation as possible to the GPU (LayerKit/CoreAnimation)
<nicolas17>
smart "display controllers" are newer stuff I know nothing about :P
roxfan2 is now known as roxfan
<jannau>
nice, iboot pre-allocates space for 10 l2 tables in pt-region-0 for disp*/dcp*. that's a little more convenient than replacing them with a new ram allocation
amarioguy has quit [Ping timeout: 480 seconds]
amarioguy has joined #asahi-dev
user982492 has joined #asahi-dev
unevenrhombus[m] has quit [Server closed connection]
unevenrhombus[m] has joined #asahi-dev
mariogrip[m] has quit [Server closed connection]
mariogrip[m] has joined #asahi-dev
Hinata[m] has quit [Server closed connection]
Hinata[m] has joined #asahi-dev
AnalogDigital[m] has quit [Server closed connection]
AnalogDigital[m] has joined #asahi-dev
davay[m] has quit [Server closed connection]
davay[m] has joined #asahi-dev
BastienSaidi[m] has quit [Server closed connection]
BastienSaidi[m] has joined #asahi-dev
bmrgz[m] has quit [Server closed connection]
bmrgz[m] has joined #asahi-dev
booffo[m] has quit [Server closed connection]
booffo[m] has joined #asahi-dev
c1truz[m] has quit [Server closed connection]
c1truz[m] has joined #asahi-dev
AnushervonTabarov[m] has quit [Server closed connection]
AnushervonTabarov[m] has joined #asahi-dev
daniel0611[m] has quit [Server closed connection]
daniel0611[m] has joined #asahi-dev
David[m]123 has quit [Server closed connection]
David[m]123 has joined #asahi-dev
dcavalca has quit [Server closed connection]
dcavalca has joined #asahi-dev
Emantor[m] has quit [Server closed connection]
Emantor[m] has joined #asahi-dev
etsukata[m] has quit [Server closed connection]
etsukata[m] has joined #asahi-dev
feeleep[m] has quit [Server closed connection]
feeleep[m] has joined #asahi-dev
hectour[m] has quit [Server closed connection]
hectour[m] has joined #asahi-dev
furrylover420[m] has quit [Server closed connection]
furrylover420[m] has joined #asahi-dev
gamble[m] has quit [Server closed connection]
gamble[m] has joined #asahi-dev
ghantaz[m] has quit [Server closed connection]
ghantaz[m] has joined #asahi-dev
javier_varez[m] has quit [Server closed connection]
javier_varez[m] has joined #asahi-dev
jeh[m] has quit [Server closed connection]
jeh[m] has joined #asahi-dev
josipknezovic[m] has quit [Server closed connection]
josipknezovic[m] has joined #asahi-dev
kedde[m] has quit [Server closed connection]
kedde[m] has joined #asahi-dev
lockna has quit [Server closed connection]
lockna has joined #asahi-dev
landscape15[m] has quit [Server closed connection]
landscape15[m] has joined #asahi-dev
LilleCarl[m] has quit [Server closed connection]
LilleCarl[m] has joined #asahi-dev
LorenzKofler[m] has quit [Server closed connection]
LorenzKofler[m] has joined #asahi-dev
matthewayers[m] has quit [Server closed connection]
matthewayers[m] has joined #asahi-dev
nirusu[m] has quit [Server closed connection]
nirusu[m] has joined #asahi-dev
DanStrong[m] has quit [Server closed connection]
DanStrong[m] has joined #asahi-dev
latko[m] has quit [Server closed connection]
latko[m] has joined #asahi-dev
PedroArajo[m] has quit [Server closed connection]
PedroArajo[m] has joined #asahi-dev
plantaintion3[m] has quit [Server closed connection]
plantaintion3[m] has joined #asahi-dev
pulpy_orange2[m] has quit [Server closed connection]
pulpy_orange2[m] has joined #asahi-dev
pwn0rz[m] has quit [Server closed connection]
pwn0rz[m] has joined #asahi-dev
quentin[m] has quit [Server closed connection]
quentin[m] has joined #asahi-dev
Redecorating[m] has quit [Server closed connection]
Redecorating[m] has joined #asahi-dev
rethematrix[m] has quit [Server closed connection]
rethematrix[m] has joined #asahi-dev
rhys has quit [Server closed connection]
rhys has joined #asahi-dev
RowanGoemans[m] has quit [Server closed connection]
RowanGoemans[m] has joined #asahi-dev
RianSouzaSantos[m] has quit [Server closed connection]
RianSouzaSantos[m] has joined #asahi-dev
ryanhrob1[m] has quit [Server closed connection]
ryanhrob1[m] has joined #asahi-dev
s-urabe[m] has quit [Server closed connection]
s-urabe[m] has joined #asahi-dev
Sebhl[m] has quit [Server closed connection]
Sebhl[m] has joined #asahi-dev
shaman_br[m] has quit [Server closed connection]
shaman_br[m] has joined #asahi-dev
sikkileo[m] has quit [Server closed connection]
sikkileo[m] has joined #asahi-dev
simjnd[m] has quit [Server closed connection]
simjnd[m] has joined #asahi-dev
SocioProphet[m] has quit [Server closed connection]
SocioProphet[m] has joined #asahi-dev
JacksonR[m] has quit [Server closed connection]
JacksonR[m] has joined #asahi-dev
spokv[m] has quit [Server closed connection]
spokv[m] has joined #asahi-dev
sppdqd[m] has quit [Server closed connection]
sppdqd[m] has joined #asahi-dev
sproede[m] has quit [Server closed connection]
sproede[m] has joined #asahi-dev
svenpeter[m] has quit [Server closed connection]
svenpeter[m] has joined #asahi-dev
therealminzii[m] has quit [Server closed connection]
therealminzii[m] has joined #asahi-dev
threerik[m] has quit [Server closed connection]
threerik[m] has joined #asahi-dev
svenpeter[m] is now known as Guest580
tophevich[m] has quit [Server closed connection]
tophevich[m] has joined #asahi-dev
user1tt[m] has quit [Server closed connection]
user1tt[m] has joined #asahi-dev
vimsos[m] has quit [Server closed connection]
vimsos[m] has joined #asahi-dev
xiaomingcc[m] has quit [Server closed connection]
xiaomingcc[m] has joined #asahi-dev
xorly[m] has quit [Server closed connection]
xorly[m] has joined #asahi-dev
m6wiq has joined #asahi-dev
the_lanetly_052 has quit [Ping timeout: 480 seconds]
Andre[m]1 has quit [Server closed connection]
Andre[m]1 has joined #asahi-dev
sunyiynus[m] has quit [Server closed connection]
sunyiynus[m] has joined #asahi-dev
ybk[m] has quit [Server closed connection]
ybk[m] has joined #asahi-dev
yamii has quit [Quit: WeeChat 3.3]
yamii has joined #asahi-dev
bisko has quit [Read error: Connection reset by peer]
bisko has joined #asahi-dev
Glanzmann has quit [Quit: leaving]
___nick___ has quit [Ping timeout: 480 seconds]
doggkruse has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
doggkruse has joined #asahi-dev
HardWall has joined #asahi-dev
m6wiq has quit []
user982492 has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
amarioguy has quit [Ping timeout: 480 seconds]
dsrt^ has joined #asahi-dev
bisko has quit [Read error: Connection reset by peer]
bisko has joined #asahi-dev
user982492 has joined #asahi-dev
user982492 has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
bisko has quit [Read error: Connection reset by peer]
bisko has joined #asahi-dev
<rqou_>
what is the DART SP_START/SP_END?
<j`ey>
sp = sub-page maybe?
<rqou_>
follow-up question: what does it do?
<rqou_>
how does it work?
<j`ey>
afaik it allows you to map part of a page
<rqou_>
i thought that didn't work? otherwise why would there be issues with 4k kernels?